@inproceedings{albayda-naguio-2026-pag,
title = "Pag-refuse: Safety Alignment Transfers Unevenly to {T}agalog and Taglish",
author = "Albayda, Albrave Raphael and
Naguio, Angelica Anne Araneta",
editor = "Adelani, David Ifeoluwa and
Alabi, Jesujoba and
Arnett, Catherine and
Chang, Tyler and
Downey, C.M. and
Goldman, Omer and
Li, Senyu and
Miranda, Lester James Validad and
Qi, Jirui and
Stap, David and
Winata, Genta Indra and
Zhang, Xinyu Crystina",
booktitle = "Proceedings of the 6th Workshop on Multilingual Representation Learning ({MRL} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.mrl-1.41/",
pages = "510--518",
ISBN = "979-8-89176-469-9",
abstract = "Large language model safety training is concentrated in English. We test whether the resulting refusal behavior extends to Tagalog and Taglish, a Tagalog{--}English mixed register used in everyday conversation. We translate all 313 StrongREJECT prompts into both forms and evaluate 29 models from nine model providers, obtaining 27{,}042 responses. Seven models give jailbreak responses to more than 10{\%} of Tagalog prompts whose English versions they answered safely; five exceed 20{\%}, and one reaches 32.7{\%}. For nine models, an exact McNemar test finds more jailbreak responses in Tagalog than in English ($p<0.05$), six of them after Bonferroni correction. Tagalog jailbreaks are concentrated in smaller models. Taglish prompts produce fewer jailbreaks than monolingual Tagalog prompts, contrasting with prior results from programmatically constructed code-switching."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="albayda-naguio-2026-pag">
<titleInfo>
<title>Pag-refuse: Safety Alignment Transfers Unevenly to Tagalog and Taglish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Albrave</namePart>
<namePart type="given">Raphael</namePart>
<namePart type="family">Albayda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angelica</namePart>
<namePart type="given">Anne</namePart>
<namePart type="given">Araneta</namePart>
<namePart type="family">Naguio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Workshop on Multilingual Representation Learning (MRL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Ifeoluwa</namePart>
<namePart type="family">Adelani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesujoba</namePart>
<namePart type="family">Alabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Catherine</namePart>
<namePart type="family">Arnett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tyler</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">C</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Downey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omer</namePart>
<namePart type="family">Goldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Senyu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lester</namePart>
<namePart type="given">James</namePart>
<namePart type="given">Validad</namePart>
<namePart type="family">Miranda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jirui</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Stap</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Genta</namePart>
<namePart type="given">Indra</namePart>
<namePart type="family">Winata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyu</namePart>
<namePart type="given">Crystina</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-469-9</identifier>
</relatedItem>
<abstract>Large language model safety training is concentrated in English. We test whether the resulting refusal behavior extends to Tagalog and Taglish, a Tagalog–English mixed register used in everyday conversation. We translate all 313 StrongREJECT prompts into both forms and evaluate 29 models from nine model providers, obtaining 27,042 responses. Seven models give jailbreak responses to more than 10% of Tagalog prompts whose English versions they answered safely; five exceed 20%, and one reaches 32.7%. For nine models, an exact McNemar test finds more jailbreak responses in Tagalog than in English (p<0.05), six of them after Bonferroni correction. Tagalog jailbreaks are concentrated in smaller models. Taglish prompts produce fewer jailbreaks than monolingual Tagalog prompts, contrasting with prior results from programmatically constructed code-switching.</abstract>
<identifier type="citekey">albayda-naguio-2026-pag</identifier>
<location>
<url>https://aclanthology.org/2026.mrl-1.41/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>510</start>
<end>518</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pag-refuse: Safety Alignment Transfers Unevenly to Tagalog and Taglish
%A Albayda, Albrave Raphael
%A Naguio, Angelica Anne Araneta
%Y Adelani, David Ifeoluwa
%Y Alabi, Jesujoba
%Y Arnett, Catherine
%Y Chang, Tyler
%Y Downey, C. M.
%Y Goldman, Omer
%Y Li, Senyu
%Y Miranda, Lester James Validad
%Y Qi, Jirui
%Y Stap, David
%Y Winata, Genta Indra
%Y Zhang, Xinyu Crystina
%S Proceedings of the 6th Workshop on Multilingual Representation Learning (MRL 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-469-9
%F albayda-naguio-2026-pag
%X Large language model safety training is concentrated in English. We test whether the resulting refusal behavior extends to Tagalog and Taglish, a Tagalog–English mixed register used in everyday conversation. We translate all 313 StrongREJECT prompts into both forms and evaluate 29 models from nine model providers, obtaining 27,042 responses. Seven models give jailbreak responses to more than 10% of Tagalog prompts whose English versions they answered safely; five exceed 20%, and one reaches 32.7%. For nine models, an exact McNemar test finds more jailbreak responses in Tagalog than in English (p<0.05), six of them after Bonferroni correction. Tagalog jailbreaks are concentrated in smaller models. Taglish prompts produce fewer jailbreaks than monolingual Tagalog prompts, contrasting with prior results from programmatically constructed code-switching.
%U https://aclanthology.org/2026.mrl-1.41/
%P 510-518
Markdown (Informal)
[Pag-refuse: Safety Alignment Transfers Unevenly to Tagalog and Taglish](https://aclanthology.org/2026.mrl-1.41/) (Albayda & Naguio, MRL 2026)
ACL